© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B-IT
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 14291
    Prev
    Next
    INDEX
    Explanations

    references to local communities and their activities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    a specific geographic area

    np_acts-logits-general · gemini-2.0-flash

    local or home origin

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     المعيارى
    -0.51
     resourceCulture
    -0.41
     MediatR
    -0.39
    ChildScrollView
    -0.37
    FormState
    -0.36
    intios
    -0.35
    期刊论文
    -0.34
    antd
    -0.32
     figure
    -0.31
    FontStyle
    -0.31
    POSITIVE LOGITS
     locally
    0.88
    Local
    0.87
     local
    0.87
    local
    0.85
     lokal
    0.84
     lokalen
    0.82
     Locally
    0.81
    locally
    0.81
     lokale
    0.79
    Locally
    0.79
    Activations Density 0.363%

    No Known Activations